Mercurial > repos > lparsons > fastq_join

comparison fastq-join.xml @ 0:2ac846969812 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded initial version with package dependency
author lparsons
date Fri, 27 Jun 2014 15:39:38 -0400
parents
children 593a729e5706
comparison
equal deleted inserted replaced
-1:000000000000 0:2ac846969812
1 <tool id="fastq_join" name="fastq-join" version="1.1.2-484">
2 <description> - Joins paired-end reads on the overlapping ends</description>
3 <requirements>
4 <requirement type="package" version="1.1.2-484">ea-utils</requirement>
5 </requirements>
6 <command>
7 fastq-join
8 -v '$splitChar'
9 -p $pctMaxDiff
10 -m $minOverlap
11 #if $stitchLengthReport:
12 -r $outputStitchLengthReport
13 #end if
14 $read1
15 $read2
16 -o $outputUnmatched1 -o $outputUnmatched2 -o $outputJoined
17 </command>
18 <inputs>
19 <param format="fastq, fastqillumina, fastqsanger, fastqsolexa" name="read1" type="data" label="Read 1 Fastq" />
20 <param format="fastq, fastqillumina, fastqsanger, fastqsolexa" name="read2" type="data" label="Read 2 Fastq" />
21 <param name="splitChar" type="text" value=" " label="Split read ids on this character" help="Default is space ' ' for Illumina reads" />
22 <param name="pctMaxDiff" type="float" value="8" min="0" max="100" label="Maximum percentage difference between matching segments" />
23 <param name="minOverlap" type="integer" value="6" min="1" label="Minimum length of matching segements" />
24 <param name="stitchLengthReport" type="boolean" value="False" label="Output verbose stitch length report" />
25 </inputs>
26
27 <outputs>
28 <data format="input" format_source="read1" name="outputJoined" label="${tool.name} on ${on_string} (joined)"/>
29 <data format="input" format_source="read1" name="outputUnmatched1" label="${tool.name} on ${on_string} (unmatched1)"/>
30 <data format="input" format_source="read2" name="outputUnmatched2" label="${tool.name} on ${on_string} (unmatched2)"/>
31 <data format="tabular" name="outputStitchLengthReport" label="${tool.name} on ${on_string} (stitch length report)">
32 <filter>stitchLengthReport</filter>
33 </data>
34 </outputs>
35
36 <stdio>
37 <exit_code range="1:" level="fatal" description="Unknown error occurred" />
38 </stdio>
39
40 <tests>
41 <test>
42 <param name="read1" value="test_read1.fastq" />
43 <param name="read2" value="test_read3.fastq" />
44 <output name="outputJoined" file="testout.join.fastq" />
45 <output name="outputUnmatched1" file="testout.un1.fastq" />
46 <output name="outputUnmatched2" file="testout.un2.fastq" />
47 </test>
48 </tests>
49
50 <help>
51 Overview
52 --------
53 fastq-join joins two paired-end reads on the overlapping ends.
54
55 Split read ids character: Verifies that the 2 files probe id's match up to char C. Use ' ' for Illumina reads.
56
57 Maximum difference is the maximum allowed percentage of bases that differ in the matching region.
58
59 Minimum overlap is the minimum number of bases that must overlap (with no more than the maximum difference) for reads to be joined.
60
61 Verbose stitch length report is a report for each joined paired of reads showing how large the overlapping section was.
62
63 This tool uses sqr(distance)/len for anchored alignment quality algorithm. It's a good measure of anchored alignment quality, akin to squared-deviation for means. This tool uses the fastq-join program that is part of the ea-utils suite. See http://code.google.com/p/ea-utils/wiki/FastqJoin for details.
64 </help>
65 </tool>